BiDFDC-Net: a dense connection network based on bi-directional feedback for skin image segmentation
Accurate segmentation of skin lesions in dermoscopic images plays an important role in improving the survival rate of patients. However, due to the blurred boundaries of pigment regions, the diversity of lesion features, and the mutations and metastases of diseased cells, the effectiveness and robus...
| Main Authors: | , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Frontiers Media S.A.
2023-06-01
|
| Series: | Frontiers in Physiology |
| Subjects: | |
| Online Access: | https://www.frontiersin.org/articles/10.3389/fphys.2023.1173108/full |
| _version_ | 1797799872189956096 |
|---|---|
| author | Jinyun Jiang Zitong Sun Qile Zhang Kun Lan Xiaoliang Jiang Jun Wu |
| author_facet | Jinyun Jiang Zitong Sun Qile Zhang Kun Lan Xiaoliang Jiang Jun Wu |
| author_sort | Jinyun Jiang |
| collection | DOAJ |
| description | Accurate segmentation of skin lesions in dermoscopic images plays an important role in improving the survival rate of patients. However, due to the blurred boundaries of pigment regions, the diversity of lesion features, and the mutations and metastases of diseased cells, the effectiveness and robustness of skin image segmentation algorithms are still a challenging subject. For this reason, we proposed a bi-directional feedback dense connection network framework (called BiDFDC-Net), which can perform skin lesions accurately. Firstly, under the framework of U-Net, we integrated the edge modules into each layer of the encoder which can solve the problem of gradient vanishing and network information loss caused by network deepening. Then, each layer of our model takes input from the previous layer and passes its feature map to the densely connected network of subsequent layers to achieve information interaction and enhance feature propagation and reuse. Finally, in the decoder stage, a two-branch module was used to feed the dense feedback branch and the ordinary feedback branch back to the same layer of coding, to realize the fusion of multi-scale features and multi-level context information. By testing on the two datasets of ISIC-2018 and PH2, the accuracy on the two datasets was given by 93.51% and 94.58%, respectively. |
| first_indexed | 2024-03-13T04:25:28Z |
| format | Article |
| id | doaj.art-08913a625c554c798eb3ccf04f268a99 |
| institution | Directory Open Access Journal |
| issn | 1664-042X |
| language | English |
| last_indexed | 2024-03-13T04:25:28Z |
| publishDate | 2023-06-01 |
| publisher | Frontiers Media S.A. |
| record_format | Article |
| series | Frontiers in Physiology |
| spelling | doaj.art-08913a625c554c798eb3ccf04f268a992023-06-20T05:15:41ZengFrontiers Media S.A.Frontiers in Physiology1664-042X2023-06-011410.3389/fphys.2023.11731081173108BiDFDC-Net: a dense connection network based on bi-directional feedback for skin image segmentationJinyun Jiang0Zitong Sun1Qile Zhang2Kun Lan3Xiaoliang Jiang4Jun Wu5College of Mechanical Engineering, Quzhou University, Quzhou, ChinaCollege of Mechanical Engineering, Quzhou University, Quzhou, ChinaDepartment of Rehabilitation, The Quzhou Affiliated Hospital of Wenzhou Medical University, Quzhou People’s Hospital, Quzhou, ChinaCollege of Mechanical Engineering, Quzhou University, Quzhou, ChinaCollege of Mechanical Engineering, Quzhou University, Quzhou, ChinaCollege of Mechanical Engineering, Quzhou University, Quzhou, ChinaAccurate segmentation of skin lesions in dermoscopic images plays an important role in improving the survival rate of patients. However, due to the blurred boundaries of pigment regions, the diversity of lesion features, and the mutations and metastases of diseased cells, the effectiveness and robustness of skin image segmentation algorithms are still a challenging subject. For this reason, we proposed a bi-directional feedback dense connection network framework (called BiDFDC-Net), which can perform skin lesions accurately. Firstly, under the framework of U-Net, we integrated the edge modules into each layer of the encoder which can solve the problem of gradient vanishing and network information loss caused by network deepening. Then, each layer of our model takes input from the previous layer and passes its feature map to the densely connected network of subsequent layers to achieve information interaction and enhance feature propagation and reuse. Finally, in the decoder stage, a two-branch module was used to feed the dense feedback branch and the ordinary feedback branch back to the same layer of coding, to realize the fusion of multi-scale features and multi-level context information. By testing on the two datasets of ISIC-2018 and PH2, the accuracy on the two datasets was given by 93.51% and 94.58%, respectively.https://www.frontiersin.org/articles/10.3389/fphys.2023.1173108/fullimage segmentationskinbi-directional feedbackdense connectionU-Net |
| spellingShingle | Jinyun Jiang Zitong Sun Qile Zhang Kun Lan Xiaoliang Jiang Jun Wu BiDFDC-Net: a dense connection network based on bi-directional feedback for skin image segmentation Frontiers in Physiology image segmentation skin bi-directional feedback dense connection U-Net |
| title | BiDFDC-Net: a dense connection network based on bi-directional feedback for skin image segmentation |
| title_full | BiDFDC-Net: a dense connection network based on bi-directional feedback for skin image segmentation |
| title_fullStr | BiDFDC-Net: a dense connection network based on bi-directional feedback for skin image segmentation |
| title_full_unstemmed | BiDFDC-Net: a dense connection network based on bi-directional feedback for skin image segmentation |
| title_short | BiDFDC-Net: a dense connection network based on bi-directional feedback for skin image segmentation |
| title_sort | bidfdc net a dense connection network based on bi directional feedback for skin image segmentation |
| topic | image segmentation skin bi-directional feedback dense connection U-Net |
| url | https://www.frontiersin.org/articles/10.3389/fphys.2023.1173108/full |
| work_keys_str_mv | AT jinyunjiang bidfdcnetadenseconnectionnetworkbasedonbidirectionalfeedbackforskinimagesegmentation AT zitongsun bidfdcnetadenseconnectionnetworkbasedonbidirectionalfeedbackforskinimagesegmentation AT qilezhang bidfdcnetadenseconnectionnetworkbasedonbidirectionalfeedbackforskinimagesegmentation AT kunlan bidfdcnetadenseconnectionnetworkbasedonbidirectionalfeedbackforskinimagesegmentation AT xiaoliangjiang bidfdcnetadenseconnectionnetworkbasedonbidirectionalfeedbackforskinimagesegmentation AT junwu bidfdcnetadenseconnectionnetworkbasedonbidirectionalfeedbackforskinimagesegmentation |